{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:55:42Z","timestamp":1764996942420,"version":"3.41.0"},"reference-count":59,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2012,6,1]],"date-time":"2012-06-01T00:00:00Z","timestamp":1338508800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["6.10E+15"],"award-info":[{"award-number":["6.10E+15"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Transactions on Asian Language Information Processing"],"published-print":{"date-parts":[[2012,6]]},"abstract":"<jats:p>\n            Among statistical approaches to Chinese word segmentation, the\n            <jats:italic>word-based n-gram<\/jats:italic>\n            (\n            <jats:italic>generative<\/jats:italic>\n            ) model and the\n            <jats:italic>character-based tagging<\/jats:italic>\n            (\n            <jats:italic>discriminative<\/jats:italic>\n            ) model are two dominant approaches in the literature. The former gives excellent performance for the\n            <jats:italic>in-vocabulary<\/jats:italic>\n            (IV) words; however, it handles\n            <jats:italic>out-of-vocabulary<\/jats:italic>\n            (OOV) words poorly. On the other hand, though the latter is more robust for OOV words, it fails to deliver satisfactory performance for IV words. These two approaches behave differently due to the unit they use (word vs. character) and the model form they adopt (generative vs. discriminative). In general, character-based approaches are more robust than word-based ones, as the vocabulary of characters is a closed set; and discriminative models are more robust than generative ones, since they can flexibly include all kinds of available information, such as future context.\n          <\/jats:p>\n          <jats:p>\n            This article first proposes a character-based\n            <jats:italic>n<\/jats:italic>\n            -gram model to enhance the robustness of the generative approach. Then the proposed generative model is further integrated with the character-based discriminative model to take advantage of both approaches. Our experiments show that this integrated approach outperforms all the existing approaches reported in the literature. Afterwards, a complete and detailed error analysis is conducted. Since a significant portion of the critical errors is related to numerical\/foreign strings, character-type information is then incorporated into the model to further improve its performance. Last, the proposed integrated approach is tested on cross-domain corpora, and a semi-supervised domain adaptation algorithm is proposed and shown to be effective in our experiments.\n          <\/jats:p>","DOI":"10.1145\/2184436.2184440","type":"journal-article","created":{"date-parts":[[2012,6,11]],"date-time":"2012-06-11T13:03:21Z","timestamp":1339419801000},"page":"1-41","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Integrating Generative and Discriminative Character-Based Models for Chinese Word Segmentation"],"prefix":"10.1145","volume":"11","author":[{"given":"Kun","family":"Wang","sequence":"first","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengqing","family":"Zong","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keh-Yih","family":"Su","sequence":"additional","affiliation":[{"name":"Behavior Design Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2012,6]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/1610075.1610140"},{"volume-title":"Proceedings of the 4th Workshop on Chinese Language Processing (SIGHAN\u201905)","author":"Asahara M.","key":"e_1_2_1_2_1"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/234285.234289"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073483.1073485"},{"key":"e_1_2_1_5_1","unstructured":"Bishop C. M. 2006. Pattern Recognition and Machine Learning. Springer New York. Bishop C. M. 2006. Pattern Recognition and Machine Learning . Springer New York."},{"volume-title":"Proceedings of the 3rd Workshop on Chinese Language Learning (SIGHAN\u201904)","author":"Chang J.-S.","key":"e_1_2_1_6_1"},{"key":"e_1_2_1_7_1","unstructured":"Chen S. F. and Goodman J. 1998. An empirical study of smoothing techniques for language modeling. Tech. rep. TR-10-98 Harvard University Center for Research in Computing Technology. Chen S. F. and Goodman J. 1998. An empirical study of smoothing techniques for language modeling. Tech. rep. TR-10-98 Harvard University Center for Research in Computing Technology."},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.3115\/1118693.1118694"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1198\/106186008X344748"},{"volume-title":"Proceedings of the 4th Workshop on Chinese Language Processing (SIGHAN\u201905)","year":"2005","author":"Emerson T.","key":"e_1_2_1_10_1"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2008.01.001"},{"volume-title":"Proceedings of the National Conference on Artificial Intelligence (AAAI\u201905)","author":"Fujino A.","key":"e_1_2_1_12_1"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.3115\/1075096.1075131"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1162\/089120105775299177"},{"volume-title":"Proceedings of the 23rd Conference on Uncertainty in Artificial Intelligence (UAI\u201907)","author":"Haffari G.","key":"e_1_2_1_15_1"},{"volume-title":"Proceedings of the 45th ACL Conference on Interactive Poster and Demonstration Sessions (ACL\u201907)","author":"Huang C.-R.","key":"e_1_2_1_16_1"},{"volume-title":"Proc. Syst. 487--493","author":"Jaakkola T. S.","key":"e_1_2_1_17_1"},{"volume-title":"Proceedings of the Language Technology Conference (NAACL\u201910)","author":"Jiampojamarn S.","key":"e_1_2_1_18_1"},{"volume-title":"Proceedings of the Association for Computational Linguistics (ACL\u201908)","author":"Jiang W.","key":"e_1_2_1_19_1"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073012.1073054"},{"volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP\u201904)","year":"2004","author":"Koehn P.","key":"e_1_2_1_21_1"},{"volume-title":"Proceedings of the 47th Annual Meetings of the ACL and the 4th IJCNLP of the AFNLP (ACL\u201909)","author":"Kruengkrai C.","key":"e_1_2_1_22_1"},{"volume-title":"Proceedings of the 18th International Conference on Machine Learning (CML\u201901)","author":"Lafferty J.","key":"e_1_2_1_23_1"},{"key":"e_1_2_1_24_1","unstructured":"Lee H. W. D. 2005. A Study of Automatic Expansion of Chinese Abbreviations. The University of Hong Kong. Lee H. W. D. 2005. A Study of Automatic Expansion of Chinese Abbreviations . The University of Hong Kong."},{"volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics (ACL\u201911)","year":"2011","author":"Li Z.","key":"e_1_2_1_25_1"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2009.35.4.35403"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390230"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.3115\/1220835.1220855"},{"volume-title":"Proceedings of the Conference on the Advances in Neural Information Processing Systems (NIPS\u201902)","author":"Ng A. Y.","key":"e_1_2_1_29_1"},{"volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP\u201904)","author":"Ng H. T.","key":"e_1_2_1_30_1"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.3115\/976909.979658"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.3115\/1220355.1220436"},{"volume-title":"Proc. Syst.","author":"Raina R.","key":"e_1_2_1_33_1"},{"volume-title":"Proceedings of IJCAI.","author":"Shi Y.","key":"e_1_2_1_34_1"},{"volume-title":"Proceedings of the International Conference on Spoken Language Processing (ICSLP\u201902)","year":"2002","author":"Stolcke A.","key":"e_1_2_1_35_1"},{"volume-title":"Proceedings of the 23rd International Conference on Computational Linguistics (COLING\u201910)","year":"2010","author":"Sun W.","key":"e_1_2_1_36_1"},{"volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics (ACL\u201911)","year":"2011","author":"Sun W.","key":"e_1_2_1_37_1"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/11940098_26"},{"volume-title":"Proceedings of the Human Language Technology Conference\/North American Chapter of the Association for Computational Linguistics (HLT\/NAACL\u201909)","author":"Sun X.","key":"e_1_2_1_39_1"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/1610075.1610155"},{"volume-title":"Proceedings of the 4th Workshop on Chinese Language Processing (SIGHAN\u201905)","author":"Tseng H.","key":"e_1_2_1_41_1"},{"volume-title":"Proceedings of the 23rd Pacific Asia Conference on Language, Information and Computation (PACLIC\u201909)","author":"Wang K.","key":"e_1_2_1_42_1"},{"volume-title":"Proceedings of the 23rd International Conference on Computational Linguistics (COLING\u201910)","author":"Wang K.","key":"e_1_2_1_43_1"},{"volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP\u201905)","author":"Wu Y.","key":"e_1_2_1_44_1"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2008.09.018"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-008-9088-7"},{"key":"e_1_2_1_47_1","first-page":"29","article-title":"Chinese word segmentation as character tagging","volume":"8","author":"Xue N.","year":"2003","journal-title":"Comp. Linguist. Chinese Lang. Proc."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.3115\/1119250.1119278"},{"key":"e_1_2_1_49_1","first-page":"97","article-title":"Rule-based word identification for Mandarin Chinese sentences-A unification approach","volume":"5","author":"Yeh C.-L.","year":"1991","journal-title":"Comp. Proc. Chinese Orient. Lang."},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.3115\/1119250.1119280"},{"volume-title":"Proceedings of the 23rd International Conference on Computational Linguistics (COLING\u201906)","author":"Zhang R.","key":"e_1_2_1_51_1"},{"volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL\u201907)","author":"Zhang Y.","key":"e_1_2_1_52_1"},{"volume-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL\u201908)","author":"Zhang Y.","key":"e_1_2_1_53_1"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00037"},{"volume-title":"Proceedings of the 4th International Conference on Language Resource and Evaluation (LREC\u201904). 2051","year":"2054","author":"Zhang Y.","key":"e_1_2_1_55_1"},{"volume-title":"Proceedings of the Pacific Asia Conference on Language, Information and Computation (PACLIC\u201906)","author":"Zhao H.","key":"e_1_2_1_56_1"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/1781134.1781135"},{"volume-title":"The CIPS-SIGHAN CLP 2010 Chinese word segmentation bakeoff. In Proceedings of CIPS-SIGHAN Joint Conference on Chinese Language Processing (CLP\u201910)","author":"Zhao H.","key":"e_1_2_1_58_1"},{"key":"e_1_2_1_59_1","unstructured":"Zong C. 2008. Statistical Natural Language Processing. Tsinghua University Press. Zong C. 2008. Statistical Natural Language Processing . Tsinghua University Press."}],"container-title":["ACM Transactions on Asian Language Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2184436.2184440","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2184436.2184440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T08:49:10Z","timestamp":1750236550000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2184436.2184440"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6]]},"references-count":59,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2012,6]]}},"alternative-id":["10.1145\/2184436.2184440"],"URL":"https:\/\/doi.org\/10.1145\/2184436.2184440","relation":{},"ISSN":["1530-0226","1558-3430"],"issn-type":[{"type":"print","value":"1530-0226"},{"type":"electronic","value":"1558-3430"}],"subject":[],"published":{"date-parts":[[2012,6]]},"assertion":[{"value":"2011-03-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2011-08-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2012-06-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}